create_project

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide minimal safety hints (readOnlyHint=false, destructiveHint=false), so the description must carry behavioral detail. It explains that the .peri.xml file is not created by this tool but by edit_interface, and clarifies path handling for design_files and sdc_files. This adds meaningful context beyond the annotations, though it does not mention side effects like overwriting or directory creation requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and information-dense, front-loading the purpose and then systematically addressing parameters. The line breaks aid readability, though bullet points or a table could improve scannability. No redundant sentences are present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (10 parameters, no output schema, no parameter descriptions in schema), the description covers most critical information: parameter semantics, path handling, and the edit_interface dependency. It does not specify error behaviors (e.g., existing project handling) or the exact return value, but these are secondary for a creation tool and not covered by annotations or schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates thoroughly. It enumerates allowed values for family (Trion | Titanium | Topaz), gives device examples (Ti375N1156, Ti60F225, T20F256), timing_model examples (C4, C3, I4), and clarifies path relativity and version defaults (verilog_2k, sv_09, vhdl_2008, vhdl_93). This transforms otherwise opaque parameters into actionable inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear, specific action: 'Create a new Efinity project .xml.' It identifies the resource and verb unambiguously, distinguishing it from siblings like update_project, list_projects, or run_flow. The inclusion of parameter families and examples reinforces the tool's identity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides contextual workflow guidance by noting that the Interface Designer file is created by the first edit_interface call before a full compile. However, it does not explicitly state when to use this tool versus alternatives (e.g., 'use create_project for new projects, update_project for modifications'), leaving some inference to the agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.